Research, plan,
code, and execute.

Ship autonomous agents in Python or JavaScript, with memory, RAG, and more than 100 models.

Get started

FROM ONE AGENTTO A WORKFORCE

Give agents a purpose.

Connect models and tools to turn an idea into an agent that can act.

Let them work together.

Build multi-agent workflows for research, planning and execution.

Keep what matters.

Bring memory and your own knowledge into the workflow with RAG.

Get started

One command.

This installs PraisonAI. When it finishes, run praisonai setup to add a provider key.

curl -fsSL https://raw.githubusercontent.com/MervinPraison/PraisonAI/main/install.sh | sh

THE INSTALLERTHEN PRAISONAI SETUP

Advanced installs

Python: pip install praisonaiagents
JavaScript: npm install praisonai
YAML: pip install praisonai praisonai agents.yaml
Key by hand: export OPENAI_API_KEY="your-key"

Installation notes in the docs

The first job

Research, then a finished table.

The repository opens on this agent. It takes a question, does the research, and returns the work. That is the use PraisonAI is built for.

01
One instruction
Tell the agent it is a senior analyst.
02
One question
Ask for the research, and for a table back.
03
The work
A finished table, ready for the next draft or the next agent.

from praisonai import Agent

agent = Agent(instructions="You are a senior data analyst.")
agent.start("Analyze the top 3 tech trends of 2026 and format as a markdown table.")

MEET YOUR FIRST AGENTUNDER A MINUTE

2M+ Downloads · 9K+ Stars

More than two million downloads, and over nine thousand stars on the repository.

View on GitHub

Research, plan,code, and execute.